subagent-authoring

Create standardized subagent definitions that delegate implementation to skills.

15|2|Updated Aug 16, 2025
One-click install
npx skills add https://github.com/aspiers/ai-config --skill subagent-authoring-aspiers
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-authoring
Source: https://github.com/aspiers/ai-config/tree/main/.claude/skills/subagent-authoring
Command: npx skills add https://github.com/aspiers/ai-config --skill subagent-authoring-aspiers

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a standardized approach to defining subagents for Claude Code and OpenCode that delegate all implementation to skills, reducing duplication and ensuring consistent delegation patterns.

Core Features & Use Cases

  • Standardizes subagent definitions for Claude Code and OpenCode with a shared delegation pattern.
  • Facilitates refactoring by converting existing agents into skill-driven delegates.
  • Improves maintainability by centralizing logic in skills and keeping agents thin.

Quick Start

Create a Claude Code agent and a matching OpenCode agent that delegate implementation to a skill.

Frequently Asked Questions about subagent-authoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I standardize subagent definitions in Claude Code and OpenCode?

Standardize subagent definitions by creating thin agent bodies that delegate all implementation logic to skills, ensuring consistent naming conventions and minimal content across Claude Code and OpenCode.

What is the delegation pattern for subagents in agent authoring?

The delegation pattern for subagents centralizes implementation logic in skills while keeping agent bodies thin, reducing duplication and enforcing a consistent structure across Claude Code and OpenCode.

How do I refactor existing agents to use skills for implementation logic?

Refactor existing agents by converting their implementation logic into skills and updating the agent bodies to delegate entirely to those skills, maintaining minimal content in the agent structure.

Can I use the same subagent delegation pattern across both Claude Code and OpenCode?

Yes, the subagent delegation pattern is designed to be shared across Claude Code and OpenCode, allowing you to create matching agents that delegate implementation to a common skill.

Why should I keep agent bodies thin and centralize logic in skills?

Keeping agent bodies thin and centralizing logic in skills improves maintainability and reduces duplication, ensuring consistent delegation patterns and standardized agent structure across platforms.

What are the limitations of the subagent delegation pattern for agent authoring?

The subagent delegation pattern requires adherence to consistent naming conventions and minimal agent body content, meaning any existing agents must be refactored to follow the standardized structure before benefiting from the approach.